mcpshield

mcpshield 一个针对未修补的 MCP STDIO 命令注入漏洞（CVE-2026-30623 系列，由 OX Security 于 2026 年 4 月披露，归为“设计问题”——无 SDK 补丁）的即插即用修复方案。只需导入一行代码，你的 Python 应用启动的每个 stdio MCP 服务器，在操作系统生成进程之前，其命令/参数/环境变量都会经过验证。 如果你是新手，请先阅读 适用范围，然后 安装 和 快速入门 将让你在两分钟内获得保护。 目录 项目状态 适用范围 安装 快速入门 选项 A：自动补丁（Python MCP 主机） 选项 B：静态检查（任何语言，零执行） 选项...

CVE-2026-12940-Langflow-Unauth-RCE

CVE-2026-12940 — Langflow OSS ≤ 1.10.1 未认证 RCE（MCP stdio 环境变量注入） 在 Langflow OSS 直至 1.10.1 的版本中存在未认证远程代码执行漏洞。用于保护 MCP stdio 服务器配置的环境变量黑名单（DANGEROUSENVVARS）遗漏了 SHELLOPTS、BASHOPTS 和 PS4。由于 MCP stdio 启动器会通过 bash -c 运行配置的命令，攻击者可以注入 SHELLOPTS=xtrace 以及 PS4 命令替换，并以 Langflow 进程用户的身份执行任意 shell 命令——无需有效的 M...

mcp-stdio-shellguard

Teil desStudioMeyer MCP Stack — Entwickelt auf Mallorca 🌴 · ⭐ wenn du es nutzt mcp-stdio-shellguard Defense-in-depth-Bundle für MCP-stdio-Server. Ummantelt childprocess.exec/spawn mit Allowlist + Sandbox + Replay-Erkennung, plus ein AST-Audit-CLI mcp-shellguard-audit, das MCP-Serverquellen auf...

CVE-2026-42271-PoC

CVE-2026-42271 — Iniezione di comandi autenticata in LiteLLM tramite endpoint di test MCP stdio LiteLLM POST /mcp-rest/test/connection e POST /mcp-rest/test/tools/list — Iniezione di comandi autenticata tramite trasporto MCP stdio. Qualsiasi chiave API valida può eseguire comandi OS arbitrari com...

GHSA-W3FX-MC44-MF6J Chainlit has command injection via MCP stdio transport that allows unauthenticated remote code execution

Am I affected? Only if your deployment sets features.mcp.enabled = true in .chainlit/config.toml. MCP has been disabled by default since v2.7.0, so most Chainlit deployments are not affected. No authentication is required: /mcp is reachable by any client that can open a session. Summary When MCP ...

CVE-2026-45018 Chainlit: Command injection via MCP stdio transport allows unauthenticated remote code execution

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the...

CVE-2026-45018

Chainlit (Python framework for conversational AI applications) is vulnerable to command injection via its MCP stdio transport in versions 2.4.0rc0 through 2.12.0 . When features.mcp.enabled is set to true, the POST /mcp endpoint is exposed without authentication . The validate_mcp_command() funct...

IBM Langflow OSS command injection vulnerability

IBM Langflow OSS is an open-source low-code visualization AI workflow building tool developed by IBM. It enables developers to quickly build, deploy, and iterate AI agents and RAG applications through drag-and-drop components. Additionally, it supports deep customization using Python to integrate...

CVE-2026-44450 Lumiverse: RCE via MCP stdio argument injection

Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code executi...

GHSA-P3M6-JR2H-HHXJ Duplicate Advisory: OpenClaw: MCP stdio server env could load dangerous startup variables from workspace config

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mj59-h3q9-ghfh. This link is maintained to preserve external references. Original Description OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server...

CVE-2026-44995

OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server configuration that allows attackers to execute arbitrary code. Malicious workspace configurations can pass dangerous startup variables like NODEOPTIONS, LDPRELOAD, or BASHENV to spawne...

CVE-2026-44995 OpenClaw < 2026.4.20 - Arbitrary Code Execution via MCP stdio Environment Variables

OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server configuration that allows attackers to execute arbitrary code. Malicious workspace configurations can pass dangerous startup variables like NODEOPTIONS, LDPRELOAD, or BASHENV to spawne...

CVE-2026-44995 OpenClaw < 2026.4.20 - Arbitrary Code Execution via MCP stdio Environment Variables

OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server configuration that allows attackers to execute arbitrary code. Malicious workspace configurations can pass dangerous startup variables like NODEOPTIONS, LDPRELOAD, or BASHENV to spawne...

CVE-2026-40933

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, due to unsafe serialization of stdio commands in the MCP adapter, an authenticated attacker can add an MCP stdio server with an arbitrary command, achieving command execution. The vulnerabilit...

LangChain-Chatchat 安全漏洞

LangChain-Chatchat is a chatbot software developed based on the LangChain framework, open-sourced by Chatchat-Space. Version 0.3.1 of LangChain-Chatchat contains a security vulnerability. This vulnerability stems from improper configuration and execution of the MCP STDIO server, which may allow...

CVE-2026-30616

Jaaz 1.0.30 contains a remote code execution vulnerability in its MCP STDIO command execution handling. A remote attacker can send crafted network requests to the network-accessible Jaaz application, causing attacker-controlled commands to be executed on the server. Successful exploitation result...

CVE-2026-39417 MaxKB: RCE via MCP stdio command injection in workflow engine

MaxKB is an open-source AI assistant for enterprise. Versions 2.7.1 and below contain an incomplete fix for CVE-2025-53928, where a Remote Code Execution vulnerability still exists in the MCP node of the workflow engine. MaxKB only restricts the referencing code path loading MCP config from the...

GO-2026-4645 WeKnora has Remote Code Execution (RCE) via Command Injection in MCP Stdio Configuration Validation in github.com/Tencent/WeKnora

WeKnora has Remote Code Execution RCE via Command Injection in MCP Stdio Configuration Validation in github.com/Tencent/WeKnora...

CVE-2026-30861

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. From version 0.2.5 to before version 0.2.10, an unauthenticated remote code execution RCE vulnerability exists in the MCP stdio configuration validation. The application allows unrestricted user...

CVE-2026-30861 WeKnora: Remote Code Execution (RCE) via Command Injection in MCP Stdio Configuration Validation

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. From version 0.2.5 to before version 0.2.10, an unauthenticated remote code execution RCE vulnerability exists in the MCP stdio configuration validation. The application allows unrestricted user...